Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GitHub Copilot Coding Agent

github.blog

Post reply on HN
Print view View original

361–370 of 372 posts

Re: GitHub Copilot Coding Agent

#361

Post by antihipocrat »

shakes_mcjunkie wrote: post #319
k3liutZu wrote: post #271

Earlier quoted context omitted.

> Meanwhile, engineers are using it for code completion and as a Google search alternative. Yep, that's the usefulness right now.

In my experience it's far less useful than simple auto complete. It makes things up for even small amounts of code that I have to pause my flow to correct. Also, without actually googling you don't get any context or understanding of what it's writing.

I found it to be more distracting recently. Suggestions that are too long or written in a different style make me lose my own thread of logic that I'm trying to weave .

I've had to switch it off for periods to maintain flow.

Re: GitHub Copilot Coding Agent

#362

Post by eterm »

djtango wrote: post #190
eterm wrote: post #68

Earlier quoted context omitted.

> Light edits are about 10 cents Some well-paid developers will excuse this with, "Well if it saved me 5 minutes, it's worth an order of magnitude than 10 cents". Which is true, however there's a big caveat: Time saved isn't time gained. You can "Save" 1,000 hours every night, but you don't actuall get those 1,000 hours back.

Huh? What happens if you stop using your washing machine and go back to hand washing everything?

If you earn more than me, then if you value "time saved" then you should pay me to take my washing off me. Because then you can save even more of your valuable time!

The more of my washing you can take off me, the more of your time you can save by then using a washing machine or laundry service!

Saving an hour of my time is a waste, when saving an hour of your time is worth so much more. So it makes economic sense for you to pay me, to take my washing off me!

( Does that better illustrate my point? )

Re: GitHub Copilot Coding Agent

#363

Post by taurath »

timrogers wrote: post #345
taurath wrote: post #193

Earlier quoted context omitted.

> In the repo where we're building the agent, the agent itself is actually the #5 contributor - so we really are using Copilot coding agent to build Copilot coding agent ;) Thats a fun stat! Are humans in the #1-4 slots? Its hard to know what processes are automated (300 repos sounds like a lot of repos!). Thank you for sharing the numbers you can. Every time a product launch is announced, I feel like its a gleeful a…

Humans are indeed in slots #1-4. After hearing feedback from the community, we’re planning to share more on the GitHub Blog about how we’re using Copilot coding agent at GitHub. Watch this space!

Wonderful thank you! It’s just so hard to filter signal vs noise rn.

Re: GitHub Copilot Coding Agent

#365

Post by ipaddr »

shepherdjerred wrote: post #199
ipaddr wrote: post #161

Earlier quoted context omitted.

The money won't be flowing forever. This will cost you $6,000 a year.

A new grad at a FANG costs ~$200k-$250k a year after benefits

If the market is new Grad at 200-250k then this product won't sell many copies.

If this product is going to be successful they are going to need the bulk of their customers at 40-100k employees.

Re: GitHub Copilot Coding Agent

#366

Post by andrekandre »

tjpnz wrote: post #181
timrogers wrote: post #61

Earlier quoted context omitted.

What I'm most excited about is allowing developers to spend more of their time working on the work they enjoy, and less of their time working on mundane, boring or annoying tasks. Most developers don't love writing tests, or updating documentation, or working on tricky dependency updates - and I really think we're heading to a world where AI can take the load of that and free me up to work on the most interesting and…

>Most developers don't love writing tests, or updating documentation, or working on tricky dependency updates - and I really think we're heading to a world where AI can take the load of that and free me up to work on the most interesting and complex problems. Where does the most come from? There's a certain sense of satisfaction in knowing I've tested a piece of code per my experience in the domain coupled with knowl…

  > There's a certain sense of satisfaction in knowing I've tested a piece of code per my experience in the domain coupled with knowledge of where we'll likely be in six months.
one of the other important points about writing unit tests isn't to just to confirm the implementation but to improve upon it through the process of writing tests and discovering additional requirements and edge cases etc (tdd and all that)

i suppose its possible at some point an ai could be complex enough to try out additional edge cases or confirm with a design document or something and do those parts as well... but idk its still after-the-fact testing instead of at design-time its less valuable imo...

Re: GitHub Copilot Coding Agent

#367

Post by mock-possum »

eterm wrote: post #68
Scene_Cast2 wrote: post #26

Earlier quoted context omitted.

Cline very visibly displays the ongoing cost of the task. Light edits are about 10 cents, and heavy stuff can run a couple of bucks. It's just that the tab accumulates faster than I expect.

> Light edits are about 10 cents Some well-paid developers will excuse this with, "Well if it saved me 5 minutes, it's worth an order of magnitude than 10 cents". Which is true, however there's a big caveat: Time saved isn't time gained. You can "Save" 1,000 hours every night, but you don't actuall get those 1,000 hours back.

So many people seem to be missing your point that I’m honestly wondering if you’re being trolled here.

Re: GitHub Copilot Coding Agent

#368

Post by miroljub »

timrogers wrote: post #346
miroljub wrote: post #274

Earlier quoted context omitted.

400 GitHub employees are using GitHub Copilot day in day out, and it comes out as #5 contributor? I wouldn't call that a success. If it is any useful, I would expect that even if a developer write 10% of their code using it, it would hold be #1 contributor in every project.

The #5 contributor thing is a stat from a single repository where we’re building Copilot coding agent.

If everyone is using Copilot, it's pretty low metrics.

Re: GitHub Copilot Coding Agent

#369

Post by Remnant44 »

ukuina wrote: post #333
adamsb6 wrote: post #232

Earlier quoted context omitted.

There's a large group of people that claim that AI tools are no good and I can't tell if they're in some niche where they truly aren't, they don't care to put any effort into learning the tools, or they're simply in denial.

Likely a Five Worlds scenario. https://www.joelonsoftware.com/2002/05/06/five-worlds/

Man, I miss Joel's blog. So much developer wisdom that is still relevant even if aged now.

Re: GitHub Copilot Coding Agent

#370

Post by ravedave5 »

timrogers wrote: post #182
OutOfHere wrote: post #64

Which model does it use? Will this let me select which model to use? I have seen a big difference in the type of code that different models produce, although their prompts may be to blame/credit in part.

At the moment, we're using Claude 3.7 Sonnet - but we're keeping our options open to experiment with other models and potentially bring in a model picker. (Source: I'm on the product team for Copilot coding agent.)

I was trying to find information on this on the internet and couldn't find any, thanks for providing. Interestingly enough Copilot coding agent on github.com repeatedly could not complete css changes correctly, when I switched to Agent mode in the project IDE with Claude 3.7 it was able to complete it in one round, so I assumed that there was a different model.
Post reply on HN